Electronic health record (EHR) systems are extremely useful for managing patients’ data and are widely disseminated in the health sector. The main problem with these systems is how to maintain the privacy of sensitive patient information. Due to not fully protecting the records from unauthorised users, EHR systems fail to provide privacy for protected health information. Weak security measures also allow authorised users to exceed their specific privileges to access medical records. Thus, some of the systems are not a trustworthy source and are undesirable for patients and healthcare providers. Therefore, an authorisation system that provides privacy when accessing patients’ data is required to address these security issues. Specifically, security and privacy precautions should be raised for specific categories of users, doctor advisors, physician researchers, emergency doctors, and patients’ relatives. Presently, these users can break into the electronic systems and even violate patients’ privacy because of the privileges granted to them or the inadequate security and privacy mechanisms of these systems. To address the security and privacy problems associated with specific users, we develop the Pseudonymization and Anonymization with the XACML (PAX) modular system, which depends on client and server applications. It provides a security solution to the privacy issues and the problem of safe-access decisions for patients’ data in the EHR. The results of theoretical and experimental security analysis prove that PAX provides security features in preserving the privacy of healthcare users and is safe against known attacks.

Recently, the use of intelligent technologies in clinical decision making in the telehealth environment has begun to play a vital role in improving the quality of patients' lives and helping reduce the costs and workload involved in their daily healthcare. In this paper, an effective medical recommendation system that uses a fast Fourier transformation-coupled machine learning ensemble model is proposed for short-term disease risk prediction to provide chronic heart disease patients with appropriate recommendations about the need to take a medical test or not on the coming day based on analysing their medical data. The input sequence of sliding windows based on the patient's time series data are decomposed by using the fast Fourier transformation in order to extract the frequency information. A bagging-based ensemble model is utilized to predict the patient's condition one day in advance for producing the final recommendation. A combination of three classifiers-artificial neural network, least squares-support vector machine, and naive bayes-are used to construct an ensemble framework. A real-life time series telehealth data collected from chronic heart disease patients are utilized for experimental evaluation. The experimental results show that the proposed system yields a very good recommendation accuracy and offers an effective way to reduce the risk of incorrect recommendations as well as reduce the workload for heart disease patients in conducting body tests every day. The results conclusively ascertain that the proposed system is a promising tool for analyzing time series medical data and providing accurate and reliable recommendations to patients suffering from chronic heart diseases.

Real-time semantic segmentation, which aims to achieve high segmentation accuracy at real-time inference speed, has received substantial attention over the past few years. However, many state-of-the-art real-time semantic segmentation methods tend to sacrifice some spatial details or contextual information for fast inference, thus leading to degradation in segmentation quality. In this paper, we propose a novel Deep Multi-branch Aggregation Network (called DMA-Net) based on the encoder-decoder structure to perform real-time semantic segmentation in street scenes. Specifically, we first adopt ResNet-18 as the encoder to efficiently generate various levels of feature maps from different stages of convolutions. Then, we develop a Multi-branch Aggregation Network (MAN) as the decoder to effectively aggregate different levels of feature maps and capture the multi-scale information. In MAN, a lattice enhanced residual block is designed to enhance feature representations of the network by taking advantage of the lattice structure. Meanwhile, a feature transformation block is introduced to explicitly transform the feature map from the neighboring branch before feature aggregation. Moreover, a global context block is used to exploit the global contextual information. These key components are tightly combined and jointly optimized in a unified network. Extensive experimental results on the challenging Cityscapes and CamVid datasets demonstrate that our proposed DMA-Net respectively obtains 77.0% and 73.6% mean Intersection over Union (mIoU) at the inference speed of 46.7 FPS and 119.8 FPS by only using a single NVIDIA GTX 1080Ti GPU. This shows that DMA-Net provides a good tradeoff between segmentation quality and speed for semantic segmentation in street scenes.